Research map / Federated learning and privacy / Privacy attacks and secure learning
Good Gradients Poison Your Model: Evading Defenses in Federated Learning via Boundary-adaptive Perturbation
Xiaojie Zhao, Jinqiao Shi, Yi Li, Junmin Huang, Chongru Fan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use BAPerturb instead of FedPerturb | model poisoning attack · MNIST (LeNet), defense FedAvg | attack success rate (1 - test accuracy): 0.3132 -> 0.7235 | Improved |
| use BAPerturb instead of FedPerturb | model poisoning attack · MNIST (LeNet), defense Multi-Krum | attack success rate (1 - test accuracy): 0.0126 -> 0.1354 | Improved |
| use BAPerturb instead of FedPerturb | model poisoning attack · Fashion-MNIST (CNN), defense Multi-Krum | attack success rate (1 - test accuracy): 0.3448 -> 0.1255 | Hurt |
| use BAPerturb instead of FedPerturb | model poisoning attack · CIFAR-10 (ResNet18), defense FedAvg | attack success rate (1 - test accuracy): 0.7649 -> 0.9000 | Improved |
| use BAPerturb instead of FedPerturb across non-IID degrees | model poisoning attack · CIFAR-10 (ResNet18), defense Multi-Krum, varying non-IID | attack success rate (1 - test accuracy) | Improved |
| use BAPerturb instead of FedPerturb across local epochs | model poisoning attack · Multi-Krum, varying malicious clients and epochs | attack success rate (1 - test accuracy) | Improved |
| apply BAPerturb against FLAME and RoseAgg | model poisoning attack · MNIST (LeNet) | attack success rate (1 - test accuracy): 0.0165 and 0.0188 | No clear effect |
Closest papers by meaning
- Model Poisoning Attacks to Federated Learning via Multi-Round Consistency (CVPR 2025 · similarity 0.89)
- FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error (ICML 2024 · similarity 0.88)
- Towards the Robustness of Differentially Private Federated Learning (AAAI 2024 · similarity 0.88)
- Competitive Advantage Attacks to Decentralized Federated Learning (NeurIPS 2025 · similarity 0.87)
- Concealing Sensitive Samples against Gradient Leakage in Federated Learning (AAAI 2024 · similarity 0.87)
- RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
